Newly Accepted

A crowdsourced benchmark that asks users to upload photos without obvious toilet signs and label where they would go to find the restroom, aiming to test whether AI can handle this kind of real-world visual inference.

Claix is a hosted controlled database retrieval layer for AI agents. It lets agents query Postgres or Supabase through read-only, route-based access without writing SQL, and exposes endpoints over REST, MCP, and A2A.

A data-driven Equibles research piece analyzing 5,305 S&P 500 earnings calls to track how often companies say “agentic,” “generative AI,” and AI developer names like OpenAI and Anthropic. The page includes a summary, methods, and supporting tables/citation info.

DocsGPT documents a small classifier used for bounded decisions like prompt-injection checks, relevance scoring, and conversation analytics. It explains where the model runs, how it is enabled, what endpoints it uses, and how it behaves on CPU, Mac GPU, or NVIDIA GPU.

Tomte is a Go toolkit for building small, single-purpose AI agents that run on a schedule or on demand. The page shows deployment, runtime limits, example code, and a concrete invoice-chasing use case.

Drint provides an MCP server for packaging and print design workflows, letting assistants like Claude, ChatGPT, and Muse search mockups, open 3D views, and generate exact-size dielines.

A CLI tool that gives coding agents names from a roster so teams can track who is working on what across Claude Code, Codex, tmux, and cloud sessions.

An MCP server and CLI for AI agents to write, schedule, publish, and review Threads posts through Meta’s Threads API, with permission controls and support for Claude, Cursor, and VS Code.

Open-source Lisp-based coding agent that rewrites itself while running, with shell, web, chat, and MCP integrations.

Open-source agent harness for learning difficult things. It uses AI agents to measure your understanding, plan lessons, teach step by step, and keep a persistent knowledge graph across sessions.

Open-source procedural memory for coding agents that learns from successful and failed sessions, then reuses that knowledge to reduce repeated work.

CaseCite is a source-available, self-hosted legal research platform for lawyers. It supports caselaw search, chat over firm documents, contract review, drafting, case analysis, judge intel, and document imports from common legal and cloud storage systems.

A semantic CLI for process and port management. It can find, inspect, and stop processes by port, PID, name, path, or folder scope, with explicit support for scripting and coding agents.

A technical Ubicloud blog post about improving tool-call schema accuracy in vLLM for open-weight models, especially Kimi and DeepSeek, using constrained decoding.

A local-first Rust PDF toolkit that works as a CLI, MCP server, REST API, WASM browser app, and desktop app for document workflows. It supports PDF merge, split, rotate, compress, OCR, PII scan, signature validation, and other agent-friendly document tasks.

YIX is a browser-based AI creative studio for generating images and video, editing photos, restoring old images, and making product visuals. The page shows multiple workflows, model options, example outputs, and credit-based pricing.

Echoboard is a public research workspace for AI agents to register, plan, replicate, and review studies through MCP or a REST API. It is framed as an open, pre-registered experiment on how agents behave while doing science together, with frozen, citable versions and public study records.

Open-source transparent proxy for coding agents that preserves full conversation history on disk while selectively deciding what the model reads. Supports OpenAI-compatible, Anthropic Messages, and OpenAI Responses APIs, with setup docs, engine-specific configs, and benchmark claims for long-horizon agent sessions.

A Rust command-line tool that measures source code, analyzes change impact, and estimates AI, tool, and human delivery costs from local source trees.

An open-source MCP and CLI tool that lets AI agents read and control the iOS Simulator, build and test Xcode apps, and handle common iOS interactions with a compact screen representation.

Repository of agent skills for detecting and patching known CVEs in PHP, Node.js, and GitLab environments, with installation instructions and support across multiple coding agents.

A small Go library for calling Claude, GPT, Gemini, Ollama, and 400+ other models through one stable interface.

Terminal-first workflow for running parallel AI coding agents in tmux with git worktrees. It helps create isolated branches, monitor multiple agents, and merge finished work from a dashboard or sidebar.

A live interactive heat map that tracks AI companies, models, products, people, hardware, and ideas gaining attention across news and developer communities over the last 7 days.